activity
20242026
collaborators
Showing cs.LGShow all

12 papers · 1 filter

cs.LG2026

Uncertainty Estimation for Molecular Diffusion Models

Paul Seij, Christian A. Naesseth, Stephan Mandt +1

Diffusion models have seen wide adoption for 3D molecular generation, yet they offer no principled signal of when a generated molecule is likely to be of low quality. We propose a…

cs.LG2026

Re-evaluating Confidence Remasking in Masked Diffusion Language Models

Stipe Frkovic, Metod Jazbec, Dan Zhang +3

Masked diffusion language models (dLLMs) have recently emerged as a competitive alternative to autoregressive language models, with the promise of faster inference via parallel tok…

cs.LG2026

A Tale of Two Temperatures: Simple, Efficient, and Diverse Sampling from Diffusion Language Models

Theo X. Olausson, Metod Jazbec, Xi Wang +4

Much work has been done on designing fast and accurate sampling for diffusion language models (dLLMs). However, these efforts have largely focused on the tradeoff between speed and…

cs.LG2026

Flow Matching for Tabular Data Synthesis

Bahrul Ilmi Nasution, Floor Eijkelboom, Mark Elliot +2

Synthetic data generation is an important tool for privacy-preserving data sharing. Although diffusion models have set recent benchmarks, flow matching (FM) offers a promising alte…

cs.LG2025

Monitoring Risks in Test-Time Adaptation

Mona Schirmer, Metod Jazbec, Christian A. Naesseth +1

Encountering shifted data at test time is a ubiquitous challenge when deploying predictive models. Test-time adaptation (TTA) methods address this issue by continuously adapting a…

cs.LG2025

Controlled Generation with Equivariant Variational Flow Matching

Floor Eijkelboom, Heiko Zimmermann, Sharvaree Vadgama +4

We derive a controlled generation objective within the framework of Variational Flow Matching (VFM), which casts flow matching as a variational inference problem. We demonstrate th…